© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 6846
    Prev
    Next
    INDEX
    Explanations

    span of decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä
    1.38
    age
    1.19
    ด
    1.09
    rik
    1.01
    ê
    1.00
    ö
    0.97
    ep
    0.96
    annya
    0.96
    व
    0.96
     a
    0.95
    POSITIVE LOGITS
     decades
    1.23
     Jahrze
    1.21
     Decade
    1.10
    فير
    1.07
    غيرة
    1.02
    _
    1.00
    نيا
    0.99
     decade
    0.97
    თვის
    0.96
     موسي
    0.94
    Activations Density 0.012%

    No Known Activations